Back to Basics: Revisiting REINFORCE-Style Optimization for Learning from Human Feedback in LLMs

Arash Ahmadian, Chris Cremer, Matthias Gallé, Marzieh Fadaee, Julia Kreutzer, Olivier Pietquin, Ahmet Üstün, Sara Hooker


Abstract
AI alignment in the shape of Reinforcement Learning from Human Feedback (RLHF) is increasingly treated as a crucial ingredient for high performance large language models. Proximal Policy Optimization (PPO) has been installed by the seminal literature as the standard method for the RL part of RLHF. However, it involves both high computational cost and sensitive hyperparameter tuning. We posit that most of the motivational principles that led to the development of PPO are less of a practical concern in RLHF and advocate for a less computationally expensive method that preserves and even increases performance. We revisit how alignment from human preferences is formulated in the context of RL. Keeping simplicity as a guiding principle, we show that many components of PPO are unnecessary in an RLHF context and that far simpler REINFORCE-style optimization variants outperform both PPO and newly proposed “RL-free” methods such as DPO and RAFT. Our work suggests that careful adaptation to LLMs alignment characteristics allows benefiting from online RL optimization at low cost.
Anthology ID:
2024.acl-long.662
Volume:
Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
Month:
August
Year:
2024
Address:
Bangkok, Thailand
Editors:
Lun-Wei Ku, Andre Martins, Vivek Srikumar
Venue:
ACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
12248–12267
Language:
URL:
https://aclanthology.org/2024.acl-long.662
DOI:
10.18653/v1/2024.acl-long.662
Bibkey:
Cite (ACL):
Arash Ahmadian, Chris Cremer, Matthias Gallé, Marzieh Fadaee, Julia Kreutzer, Olivier Pietquin, Ahmet Üstün, and Sara Hooker. 2024. Back to Basics: Revisiting REINFORCE-Style Optimization for Learning from Human Feedback in LLMs. In Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 12248–12267, Bangkok, Thailand. Association for Computational Linguistics.
Cite (Informal):
Back to Basics: Revisiting REINFORCE-Style Optimization for Learning from Human Feedback in LLMs (Ahmadian et al., ACL 2024)
Copy Citation:
PDF:
https://preview.aclanthology.org/nschneid-patch-5/2024.acl-long.662.pdf